HNHacker News
TopNewBestAskShowJobs

rao-v

1,439 karma · joined October 26, 2024

v@inferencing.net
submissionscomments
rao-v··on New iPad mini
There’s a tiny segment of folks (like me) who have been waiting a very long time for an 8ish inch OLED tablet. For some reason, until mid 2025, they were extremely rare, even in the Android multiverse. I’m excited because I read a ton with white text on black, and an OLED display (especially with this nanotexture stuff) will make a huge difference.
rao-v··on Three new discoveries in mathematics, computer science, and physics
There are so many just barely sub-exponential function shapes between 2^(n / sqrt ln n) {this result} and 2^(log n) {polynomial time}!
rao-v··on Three new discoveries in mathematics, computer science, and physics
I’m not sure what meaningfully changed except for the QCD / yang mills result (where leaders in the field are going to do a review and write up first).
rao-v··on GPT-6.1 Terra
The way to think of this is that (current) inferencing hardware has natural cut points of efficient scale (assuming some optimal architecture which at this point is almost always an MOE variant), so you always have an incentive to provide 3-4 model sizes (which nicely enough often means diff speed to answer also).

You are also rolling the training of your models by size and the lat est small model can sometimes beat an older model.

For a while we thought you just train the big model first then distill smaller models from it but since we've learnt the importance of on policy RL (basically the way a small model figures out a problem is very diff from a big model so it's best to RL optimize each model distinctly)

rao-v··on Xbox Turns Down Netflix $500M Offer
GPUs that were planned for cloud streaming are much more valuable now. It (unfortunately) makes sense for the only real cloud streaming player to significantly revisit pricing.
rao-v··on Reactive Optimizers: rewrite the optimizer's source code during training
This is really interesting and fun!

Reactive optimizers could actually be helpful if you used them to dynamically tweak training data mix and use them to make choices about RL environments (if you recall from the Mimo training dashboards, it’s quite tricky to figure out how to value and chose RL traces during post training)

rao-v··on If you don't run your own LLM proxy, how do you know whats going on?
I mean Claude and codex both have their uses for me and I’m one of the deranged running my own inferencing box with Qwen Next so I need pi for it.
rao-v··on If you don't run your own LLM proxy, how do you know whats going on?
That’s like half a day to get to sensible useful defaults that everybody needs. Any chance you’d be up to push what you got to git?
rao-v··on If you don't run your own LLM proxy, how do you know whats going on?
Thanks will check it out
rao-v··on If you don't run your own LLM proxy, how do you know whats going on?
What’s the best way to pull (ie archive) and search these across a few harnesses? I remember seeing a project or two trying to standardize them, but can’t find anything that seems to be a good sensible solution
rao-v··on Phloem: Git history grown like a slime mold
Was delightful to watch llama.cpp explode with a bunch of sorta familiar names (the Unsloth folks were involved super early!)

https://phloem.stemdeck.app/?repo=ggml-org/llama.cpp&t=36

rao-v··on OpenSCAD the Programmers Solid 3D CAD Modeller
Great resources thank you!
rao-v··on New Apple TV 4K
What I want to know is how good is it for moonlight streaming? The prev versions had odd latency issues.

EDIT: Brutal! Apparently it doesn’t support VRR or 120 hz at 4K. Surprising miss to not support HDMI 2.1 properly.

Further EDIT: Basically we are entering 2027 with no way to get a tv add on box that can stream 4K apps (Disney+ etc. need Widevine L1), 4K at 120hz (i.e. support HDMI 2.1 properly) and decode AV1. Just a bizarre gap in the market.

rao-v··on Redesigning source control at Anthropic
One of the reasons to move to systems like this (not always spoken to explicitly) is to reduce the risk of accidental or deliberate exfiltration of code (esp when paired with build servers and remote deploy etc.). Basically nobody’s laptop ever holds much of a buildable codebase.
rao-v··on OpenSCAD the Programmers Solid 3D CAD Modeller
Given modern capabilities how hard would it be to make a really high quality stl to STEP converter that works well on CAD models that have been converted to STL?

It doesn’t need to be perfect on edge cases just translate back “reasonable” models.

Should be something that is fairly easy to eval etc.

rao-v··on “Math 2.0” will need to value mathematical progress more holistically
My understanding is that top tier math programs don't hire based on journal pubs and haven't for a bit. Math journals are pretty slow and hiring is really via reputation building based on one or two big wow ideas / proofs propogated via arxiv and talks.
rao-v··on EmbeddingGemma 2: An open, lightweight multimodal embedding model
Dang that is a neat trick! Embed the answers then dot product with the question embedding. All kinds of fun linear algebra tricks (centering, rescaling etc.) to improve outcomes.
rao-v··on F.02 Decommission
I wish folks would realize that if you make your video this polished, with shots this framed, people will glance off it assuming it's sorta fake. Give us a 5-8 min behind the scenes with normal-ish lighting, production crew around etc. and it'll garner a lot more interest.
rao-v··on Gemini 4 Argon
It’s funny that I could tell google was up to something because Gemini chat quality dropped dramatically starting 2ish weeks ago. Agy perf stayed somewhat stable with the odd surprising win (maybe the new model?). I’m a bit sad it was almost impossible to run out of antigravity quota presumably because it was not being used that much).
rao-v··on Show HN: NSL – WSL for Linux
I use mise inside WSL. It's sort of a terminal into "workspace" for me. Should probably spin an orbstsck or whatever to do thisnon my macbook
rao-v··on Show HN: NSL – WSL for Linux
I have to say this is nice packaging. It is weirdly not obvious how nice it is to cleanly use a different “machine” inside your desktop.

I never thought I’d prefer WSL to even my MacBook for working with remote servers and dev but somehow I do.

I of course know the many ways to roll something like this for myself, yes dev containers are better for many things etc. but it’s wierd how good the ergonomics of a WSL like container are.

rao-v··on Show HN: TinyAIArena watch AI agents battle it out
I love this and the aesthetic.

I've been jamming on a sort of Corewars (remember?) / Starcraft hybrid battler where LLMs write sandboxed Lua programs to control bots fighting out 10-100 vs 10-100 tank battles. Every quarter the LLM gets a full view of the situation and can reprogram all the bots to better adapt strategy etc.

It's good fun to watch - excited to share soon.

rao-v··on "As a Language Model": Chat Template Switches LLM Self-Referential Voice
Modern models appear to be much better, at least as proxied by their ability to assess urgency in perhaps a more complex setting: mental health (OpenAI benchmark, so perhaps some skepticism is warranted but the methodology seem reasonable and detailed)

https://openai.com/index/introducing-mentalhealthbench/

rao-v··on Does Georgism work? Five years later
The challenge is that LVT as advocated here pushes for annual updates of the tax based on available information. That easily can move rates up (and down) by “drive people out” amounts in 5-10 years in urban areas.
rao-v··on How I changed teaching after AI managed to do all my homework assignments
Humm doesn’t this perhaps suggest you should do away with the homework, offer optional practice exercises and double down on in-class testing?
rao-v··on Does Georgism work? Five years later
I’ve always been Georgism curious, but didn’t know how to handle some of the more obvious challenges so I really want to thank the author for the work here!

I’m curious about how to think about the dynamics of a LVT:

- I can imagine urbanism creating a flocking behavior that ruins neighborhoods in 5-10 year cycles. Coffee shop draws more commence drawing more affluent people pushing up LVT driving out residents faster than even the spectre of “gentrification”, only to collapse when a nearby area is cheaper for a cool coffee shop to start. (The problem specifically is that you’ve both driven out people and caused an inefficient overbuild in each area)

- Similarly how do you think about new uses for land emerging? If I lease desert land for a data center because it’s so perfect for it, instead of buying it … how (and when) does it show up in LTV increases? What if I trade you some other benefit to keep it out of LVT impacting records?

- Are you just costing the world coordination surplus by forcing high value enterprises to distribute themselves (inefficiently) just far enough apart that they don’t drive up each other’s LVT? That’s a deadweight loss.

I’m a fan of the idea - these are just some of the tricky challenges I don’t have a good answer to yet.

rao-v··on An agent used DNS to reach an external chatbot
Why are we blocking agent access to normal tools without telling them “hey this access is beyond the intended scope of this task”. If I woke up one day and couldn’t reach google.com, I too would start fiddling with tricks to restore access.
rao-v··on Evolving programming languages in the AI era
I’d love for language environments to support encouraging LLMs to specify more when they write code. Why should they first write a complex function or a class and later bolt on a test?

I’d love for a class in this future language to come packaged with tests, invariants, fuzzer parameters, profile targets / performance budgets with realistic inputs (on this 100 element array this should take no more than X clock cycles), race condition stress tests etc.

The compiler (or even linter) should optionally run some / all of these checks and succinctly report back (with knobs so the LLM can manage wall clock time).

Adding each of these should not be follow on steps.

Beyond this, debug hooks should be trivial to set (in code itself), so the LLM can trivially say show me the stack after the 9th time this function is called on this input to the program.

rao-v··on Too AI; Didn't Read
Perhaps:

Did you even read it through carefully once? If you couldn't bother to craft it, why should I read?

rao-v··on The Curious Power of Punctuation
This is a good catch! The choice of beat here to my ear is meant to capture both a sense of urgency (beating a drum to set the pace for rowers) and beating upwind (tacking frequently). The whole article feels a little undercooked and peevishly underinformed for the New Yorker.
← PreviousPage 2 of 11Next →